Introduction
Linear regression
Introduction:
The Nature and Purpose of Econometrics
mathematics statistics
economics
Econometrics is an economic science, which applies the statistical and
mathematical methods for analysing the economic data to offer an
empirical content to the economic theories and for verifying them.
What is Econometrics?
Literal meaning is measurement in economics.
1932, in USA  Society of Econometrics  review Econometrica in 1933
The phases of an econometric approach in
70 years
1 Economic Theory
4 or economic model
Initial economic 2 Econometric model 3 Observed
data or empirical evaluation Data
of economic theory
5 Estimating model
Testing hypothesis of
6 economic model
Model using
7 for decisions and
forecasting
Reviewed phases diagram of an
econometric analysis
Economic Theory
Econometric Data
Model
Estimating
Testing and
checking
NO
Is the model
suitable
? YES
Testing hypothesis
Using the model
for analyses, control,
forecasting
Steps involved in the formulation of
econometric models
Economic or Financial Theory (Previous Studies)
Formulation of an Estimable Theoretical Model
Collection of Data
Model Estimation
Is the Model Statistically Adequate?
No Yes
Reformulate Model Interpret Model
Use for Analysis
Regression analysis
It is concerned with describing and evaluating
the relationship between a given variable
(usually called the dependent variable) and one
or more other variables (usually known as the
independent variable(s)).
Regression analysis (cont.)
Denote the dependent variable by y and the
independent variable(s) by x
1
, x
2
, ... , x
k
where there
are k independent variables.
Some alternative names for the y and x variables:
y x
dependent variable independent variable
explained variable explanatory variable
Note that there can be many x variables but we are
going to limit ourselves to the case where there is
only one x SIMPLE REGRESSION ANALYSIS.
Simple regression
In regression, the y variable is assumed to be
random or stochastic in some way, i.e. to
have a probability distribution. The x variables
are, however, assumed to have fixed (non
stochastic) values in repeated samples.
Examples:
Estimating a firms exposure to exchange rate risk.
Estimating the size effect in the stock market.
Evaluating selection ability of a fund manager.
Simple regression  example
Suppose that we have the following data on the consumption expenditure
per week together with the family weekly income (euro/week):
We have some intuition about the relation between the consumption
expenditure and the family income. Which variable is the dependent? The
first stage would be to form a scatter plot of the two variables.
Consumption, yi Income, xi
70 80
65 100
90 120
95 140
110 160
115 180
120 200
140 220
155 240
150 260
Simple regression example (cont.)
scatter plot
Correlation consumption  income
40
60
80
100
120
140
160
180
50 100 150 200 250 300
income (euro/week)
c
o
n
s
u
m
p
t
i
o
n
(
e
u
r
o
/
w
e
e
k
)
Simple regression (cont.)
How can we model this relationship? Use the general equation
for a straight line,
y^ = a + bx
to get the line that best fits the data.
However, this equation is completely deterministic.
We need to add a random disturbance term, into the equation.
y
t
= o + x
t
+
t
where t = 1, n
Simple regression (cont.)
The residual term captures:
We always leave out some determinants of y
t
There may be errors in the measurement of y
t
that
cannot be modelled.
Random outside influences on y
t
which we cannot
model
Simple regression determing the
intercept and the slope
Choose o (the intercept) and  (the slope) so that the
(vertical) distances from the data points to the fitted
lines are minimised:
y
x
Simple regression OLS
Ordinary Least Squares The regression coefficients
are found by minimising the sum of the squared
residuals (SSR).
Let
y
t
denote the actual data point t
denote the fitted value from the
regression line
denote the residual, y
t

t
y
t
e
t
y
OLS (1)
Regression equation for population
or
Regression equation for sample
The residuals are:
i i i
x a a y c + + =
1 0 t t t
x a a y c + + =
1 0
i i i i i
e y e x a a y + = + + =
1 0
i i i i i
x a a y y y e
1 0
= =
OLS (2)
Minimise . This is known as the residual sum of squares,
RSS (or SSR).
Minimising is equivalent with minimising
with respect to and .
=
n
t
t
e
1
2
( )
2
t t
y y
2
t
e
0
a
1
a
( )
= =
= =
n
n i
n
n i
i i i
y y e 0 ( )
= =
=
n
i
n
i
i i i
y y e
1 1
2
2